Accelerating Convolutional Neural Networks for Continuous Mobile Vision via Cache Reuse

12/01/2017
by   Mengwei Xu, et al.
0

Convolutional Neural Network (CNN) is the state-of-the-art algorithm of many mobile vision fields. It is also applied in many vision tasks such as face detection and augmented reality on mobile devices. Though benefited from the high accuracy achieved via deep CNN models, nowadays commercial mobile devices are often short in processing capacity and battery to continuously carry out such CNN-driven vision applications. In this paper, we propose a transparent caching mechanism, named CNNCache, that can substantially accelerate CNN-driven mobile continuous vision tasks without any efforts from app developers. To cache and reuse the computations of the similar image regions which are consecutively captured by mobile devices, CNNCache leverages two novel techniques: an image matching algorithm that quickly identifies similar image regions between images, and a cache-aware CNN inference engine that propagates the reusable regions through varied layers and reuses the computation results at layer granularity. We implement a prototype of CNNCache to run on commodity Android devices, and evaluate it via typical CNN models. The results show that CNNCache can accelerate the execution of CNN models by 20.2 to 47.1

READ FULL TEXT

page 3

page 5

page 8

research
12/21/2015

Quantized Convolutional Neural Networks for Mobile Devices

Recently, convolutional neural networks (CNN) have demonstrated impressi...
research
03/29/2018

Euphrates: Algorithm-SoC Co-Design for Low-Power Mobile Continuous Vision

Continuous computer vision (CV) tasks increasingly rely on convolutional...
research
01/03/2020

High Performance Depthwise and Pointwise Convolutions on Mobile Devices

Lightweight convolutional neural networks (e.g., MobileNets) are specifi...
research
09/27/2017

Modeling the Resource Requirements of Convolutional Neural Networks on Mobile Devices

Convolutional Neural Networks (CNNs) have revolutionized the research in...
research
07/01/2023

MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications

Traditionally, convolutional neural networks (CNN) and vision transforme...
research
04/27/2019

Accelerating Proposal Generation Network for Fast Face Detection on Mobile Devices

Face detection is a widely studied problem over the past few decades. Re...
research
07/23/2018

CNN-based Facial Affect Analysis on Mobile Devices

This paper focuses on the design, deployment and evaluation of Convoluti...

Please sign up or login with your details

Forgot password? Click here to reset